| 摘要 |
A voice or sound recognition system includes a microphone (1) for converting a voice into an electrical voice signal, processing means (12, 13) for generating a voice pattern in the form of a time-frequency distribution, and an identifying unit (17) for matching the voice pattern with registered voice patterns. The processing means (13) also provides a voice power signal which is supplied to a voice interval detector (14) and also to a power calculator (15) where the power signal is added frame by frame when the voice power signal exceeds a threshold. The added result is then supplied to a comparator (16) where it is compared with upper and lower reference values, and a cancel signal for cancelling the further processing of the current voice pattern is supplied to the identifying unit (17) when the added result is outside the range between the upper and lower reference values. <IMAGE> |
